© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24171
    Prev
    Next
    INDEX
    Explanations

    prop or shore

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sh
    2.94
     ش
    1.54
    sh
    1.51
     Sh
    1.37
     ш
    1.32
    Sh
    1.22
     শ
    1.16
    し
    1.11
     श
    1.07
     shunt
    1.05
    POSITIVE LOGITS
     prop
    0.84
    Shore
    0.80
     Shore
    0.79
     shore
    0.75
    岸
    0.57
    prop
    0.55
     Prop
    0.55
    shore
    0.54
    Prop
    0.52
     PROP
    0.50
    Activations Density 0.107%

    No Known Activations